Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +85 -0
- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_state.json +2134 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"decoder_sparse_step": 1,
|
| 9 |
+
"eos_token_id": 151643,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 6144,
|
| 15 |
+
"max_position_embeddings": 32768,
|
| 16 |
+
"max_window_layers": 48,
|
| 17 |
+
"mlp_only_layers": [],
|
| 18 |
+
"model_type": "qwen3_moe",
|
| 19 |
+
"moe_intermediate_size": 768,
|
| 20 |
+
"norm_topk_prob": true,
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_experts": 128,
|
| 23 |
+
"num_experts_per_tok": 8,
|
| 24 |
+
"num_hidden_layers": 48,
|
| 25 |
+
"num_key_value_heads": 4,
|
| 26 |
+
"output_router_logits": false,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_scaling": null,
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"router_aux_loss_coef": 0.001,
|
| 31 |
+
"sliding_window": null,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"torch_dtype": "bfloat16",
|
| 34 |
+
"transformers_version": "4.52.0.dev0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 151936
|
| 38 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.52.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce3edc61ee5d8e00cdd255bc34b599d13a210ed9536b9f0275f7532096e80106
|
| 3 |
+
size 4997184968
|
model-00002-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebddfad9c742142c3cdf9899c3efa3fe01714c54d5c3f0f69389a5f7838b87ed
|
| 3 |
+
size 4997741608
|
model-00003-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae44b75850ba155dfe6d35b7984f15c7145dfc2a9d487e11170edbeea7bff25d
|
| 3 |
+
size 4997742208
|
model-00004-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2644e7354a5f2df1de3c5f9f5ab968960aa3957224bd3620b5decd52767b30b0
|
| 3 |
+
size 4997743184
|
model-00005-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:102441c807e5ddbd985919aac96d583f5de7f089362f758ac8c7eef22947af3b
|
| 3 |
+
size 4997743184
|
model-00006-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21f559bca144cc025bc979376de1692052f4850cebbf8a304498cb6f7d50a2f1
|
| 3 |
+
size 4997743184
|
model-00007-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b15695d2f337e2c883113d6d5a5bb31d176fd06bfa90ef6d8c32fe5b65b78054
|
| 3 |
+
size 4997743184
|
model-00008-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed1353147fa0bb6f1c6e1e54921323718ab5db97806e0b2c16b44e06bbce4b9e
|
| 3 |
+
size 4997743184
|
model-00009-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c28f45771be003b06f6fce5012770b6eef232e815c1ef0a6e33933ba0518bba
|
| 3 |
+
size 4997743184
|
model-00010-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac1cafab7067f85ef31147ce87a4e672e86ae61bfae57b9e4e06f0dc70e3d3c
|
| 3 |
+
size 4997743184
|
model-00011-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2673dadf317c269f2b8cc75abc9d62c7ff72bffc432fa5338460c235ae9fbe4
|
| 3 |
+
size 4997743184
|
model-00012-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a772a6022446d63c73ffc524d2d8dc474be376927ab7caebc482e2ce74e22991
|
| 3 |
+
size 4997743184
|
model-00013-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9643fadefce95a97d96df0be99504f07b8d1427d51c2878fd195e451ad758d34
|
| 3 |
+
size 1094220288
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5420054200542005,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 300,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0018066847335140017,
|
| 14 |
+
"grad_norm": 2.8330458831358536,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.8251,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0036133694670280035,
|
| 21 |
+
"grad_norm": 2.881506507345633,
|
| 22 |
+
"learning_rate": 1.0714285714285714e-06,
|
| 23 |
+
"loss": 0.8284,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.005420054200542005,
|
| 28 |
+
"grad_norm": 2.864957143736817,
|
| 29 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 30 |
+
"loss": 0.8427,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.007226738934056007,
|
| 35 |
+
"grad_norm": 2.789658157036283,
|
| 36 |
+
"learning_rate": 3.2142857142857143e-06,
|
| 37 |
+
"loss": 0.8378,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.009033423667570008,
|
| 42 |
+
"grad_norm": 2.5748296264473147,
|
| 43 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 44 |
+
"loss": 0.8226,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01084010840108401,
|
| 49 |
+
"grad_norm": 2.1226324001162262,
|
| 50 |
+
"learning_rate": 5.357142857142857e-06,
|
| 51 |
+
"loss": 0.8096,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.012646793134598013,
|
| 56 |
+
"grad_norm": 1.4591614339485137,
|
| 57 |
+
"learning_rate": 6.428571428571429e-06,
|
| 58 |
+
"loss": 0.7738,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.014453477868112014,
|
| 63 |
+
"grad_norm": 1.3910404074529026,
|
| 64 |
+
"learning_rate": 7.5e-06,
|
| 65 |
+
"loss": 0.7731,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.016260162601626018,
|
| 70 |
+
"grad_norm": 1.2975941991178286,
|
| 71 |
+
"learning_rate": 8.571428571428571e-06,
|
| 72 |
+
"loss": 0.7653,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.018066847335140017,
|
| 77 |
+
"grad_norm": 2.39949931335525,
|
| 78 |
+
"learning_rate": 9.642857142857144e-06,
|
| 79 |
+
"loss": 0.7503,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.01987353206865402,
|
| 84 |
+
"grad_norm": 2.339166039208163,
|
| 85 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 86 |
+
"loss": 0.7353,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02168021680216802,
|
| 91 |
+
"grad_norm": 2.2235135720121253,
|
| 92 |
+
"learning_rate": 1.1785714285714286e-05,
|
| 93 |
+
"loss": 0.7488,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.023486901535682024,
|
| 98 |
+
"grad_norm": 1.8641369164869521,
|
| 99 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 100 |
+
"loss": 0.7252,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.025293586269196026,
|
| 105 |
+
"grad_norm": 1.7375311366152815,
|
| 106 |
+
"learning_rate": 1.3928571428571429e-05,
|
| 107 |
+
"loss": 0.7282,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.02710027100271003,
|
| 112 |
+
"grad_norm": 1.4297603171733615,
|
| 113 |
+
"learning_rate": 1.5e-05,
|
| 114 |
+
"loss": 0.7175,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.028906955736224028,
|
| 119 |
+
"grad_norm": 1.1151402205703254,
|
| 120 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 121 |
+
"loss": 0.7016,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03071364046973803,
|
| 126 |
+
"grad_norm": 0.8024202349277224,
|
| 127 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 128 |
+
"loss": 0.6998,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.032520325203252036,
|
| 133 |
+
"grad_norm": 0.7606508999595812,
|
| 134 |
+
"learning_rate": 1.8214285714285712e-05,
|
| 135 |
+
"loss": 0.6884,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.03432700993676603,
|
| 140 |
+
"grad_norm": 0.7625534222641119,
|
| 141 |
+
"learning_rate": 1.928571428571429e-05,
|
| 142 |
+
"loss": 0.6829,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.036133694670280034,
|
| 147 |
+
"grad_norm": 0.6694670087645954,
|
| 148 |
+
"learning_rate": 2.0357142857142858e-05,
|
| 149 |
+
"loss": 0.6597,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.037940379403794036,
|
| 154 |
+
"grad_norm": 0.5962751724140051,
|
| 155 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 156 |
+
"loss": 0.6656,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.03974706413730804,
|
| 161 |
+
"grad_norm": 0.574939617107255,
|
| 162 |
+
"learning_rate": 2.25e-05,
|
| 163 |
+
"loss": 0.6544,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04155374887082204,
|
| 168 |
+
"grad_norm": 0.5740495615931904,
|
| 169 |
+
"learning_rate": 2.357142857142857e-05,
|
| 170 |
+
"loss": 0.655,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04336043360433604,
|
| 175 |
+
"grad_norm": 0.5401386924725768,
|
| 176 |
+
"learning_rate": 2.464285714285714e-05,
|
| 177 |
+
"loss": 0.6603,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.045167118337850046,
|
| 182 |
+
"grad_norm": 0.5411734137719719,
|
| 183 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 184 |
+
"loss": 0.6417,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.04697380307136405,
|
| 189 |
+
"grad_norm": 0.4707448281296468,
|
| 190 |
+
"learning_rate": 2.6785714285714288e-05,
|
| 191 |
+
"loss": 0.6565,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.04878048780487805,
|
| 196 |
+
"grad_norm": 0.4601634980551412,
|
| 197 |
+
"learning_rate": 2.7857142857142858e-05,
|
| 198 |
+
"loss": 0.6344,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.05058717253839205,
|
| 203 |
+
"grad_norm": 0.4576924664211419,
|
| 204 |
+
"learning_rate": 2.892857142857143e-05,
|
| 205 |
+
"loss": 0.637,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.052393857271906055,
|
| 210 |
+
"grad_norm": 0.44420515620753975,
|
| 211 |
+
"learning_rate": 3e-05,
|
| 212 |
+
"loss": 0.6484,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.05420054200542006,
|
| 217 |
+
"grad_norm": 0.41258566428029175,
|
| 218 |
+
"learning_rate": 2.9999731440137413e-05,
|
| 219 |
+
"loss": 0.6488,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.05600722673893405,
|
| 224 |
+
"grad_norm": 0.3492774187256118,
|
| 225 |
+
"learning_rate": 2.9998925770166232e-05,
|
| 226 |
+
"loss": 0.6377,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.057813911472448055,
|
| 231 |
+
"grad_norm": 0.38161813042837406,
|
| 232 |
+
"learning_rate": 2.9997583018935875e-05,
|
| 233 |
+
"loss": 0.6262,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.05962059620596206,
|
| 238 |
+
"grad_norm": 0.3667873345432628,
|
| 239 |
+
"learning_rate": 2.9995703234527553e-05,
|
| 240 |
+
"loss": 0.6358,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.06142728093947606,
|
| 245 |
+
"grad_norm": 0.3431907596759456,
|
| 246 |
+
"learning_rate": 2.999328648425255e-05,
|
| 247 |
+
"loss": 0.6233,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.06323396567299007,
|
| 252 |
+
"grad_norm": 0.36189091112235033,
|
| 253 |
+
"learning_rate": 2.999033285464982e-05,
|
| 254 |
+
"loss": 0.6288,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06504065040650407,
|
| 259 |
+
"grad_norm": 0.3804643814225747,
|
| 260 |
+
"learning_rate": 2.9986842451482876e-05,
|
| 261 |
+
"loss": 0.6248,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.06684733514001806,
|
| 266 |
+
"grad_norm": 0.35830891965133377,
|
| 267 |
+
"learning_rate": 2.9982815399736008e-05,
|
| 268 |
+
"loss": 0.6297,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.06865401987353206,
|
| 273 |
+
"grad_norm": 0.349837532228719,
|
| 274 |
+
"learning_rate": 2.9978251843609816e-05,
|
| 275 |
+
"loss": 0.6219,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.07046070460704607,
|
| 280 |
+
"grad_norm": 0.40406566853435366,
|
| 281 |
+
"learning_rate": 2.9973151946516027e-05,
|
| 282 |
+
"loss": 0.6243,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.07226738934056007,
|
| 287 |
+
"grad_norm": 0.30908023037541016,
|
| 288 |
+
"learning_rate": 2.996751589107167e-05,
|
| 289 |
+
"loss": 0.6123,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.07407407407407407,
|
| 294 |
+
"grad_norm": 0.3499175700089795,
|
| 295 |
+
"learning_rate": 2.9961343879092512e-05,
|
| 296 |
+
"loss": 0.6186,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07588075880758807,
|
| 301 |
+
"grad_norm": 0.29453754657609377,
|
| 302 |
+
"learning_rate": 2.9954636131585845e-05,
|
| 303 |
+
"loss": 0.6117,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.07768744354110207,
|
| 308 |
+
"grad_norm": 0.31600841861885537,
|
| 309 |
+
"learning_rate": 2.9947392888742566e-05,
|
| 310 |
+
"loss": 0.6117,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.07949412827461608,
|
| 315 |
+
"grad_norm": 0.3022084890043788,
|
| 316 |
+
"learning_rate": 2.993961440992859e-05,
|
| 317 |
+
"loss": 0.6056,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.08130081300813008,
|
| 322 |
+
"grad_norm": 0.3192692448247662,
|
| 323 |
+
"learning_rate": 2.993130097367553e-05,
|
| 324 |
+
"loss": 0.613,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.08310749774164408,
|
| 329 |
+
"grad_norm": 0.2995609365814746,
|
| 330 |
+
"learning_rate": 2.9922452877670775e-05,
|
| 331 |
+
"loss": 0.6145,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.08491418247515808,
|
| 336 |
+
"grad_norm": 0.28359568489888487,
|
| 337 |
+
"learning_rate": 2.991307043874677e-05,
|
| 338 |
+
"loss": 0.6171,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.08672086720867209,
|
| 343 |
+
"grad_norm": 0.2763705613050705,
|
| 344 |
+
"learning_rate": 2.9903153992869734e-05,
|
| 345 |
+
"loss": 0.6031,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.08852755194218609,
|
| 350 |
+
"grad_norm": 0.3024771650885143,
|
| 351 |
+
"learning_rate": 2.989270389512756e-05,
|
| 352 |
+
"loss": 0.6108,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.09033423667570009,
|
| 357 |
+
"grad_norm": 0.2961191333250206,
|
| 358 |
+
"learning_rate": 2.988172051971717e-05,
|
| 359 |
+
"loss": 0.61,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.0921409214092141,
|
| 364 |
+
"grad_norm": 0.2832954078297925,
|
| 365 |
+
"learning_rate": 2.9870204259931062e-05,
|
| 366 |
+
"loss": 0.5999,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.0939476061427281,
|
| 371 |
+
"grad_norm": 0.28528145590927906,
|
| 372 |
+
"learning_rate": 2.9858155528143256e-05,
|
| 373 |
+
"loss": 0.617,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.0957542908762421,
|
| 378 |
+
"grad_norm": 0.31958273903448986,
|
| 379 |
+
"learning_rate": 2.9845574755794522e-05,
|
| 380 |
+
"loss": 0.6027,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.0975609756097561,
|
| 385 |
+
"grad_norm": 0.2721806575699711,
|
| 386 |
+
"learning_rate": 2.9832462393376926e-05,
|
| 387 |
+
"loss": 0.5922,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0993676603432701,
|
| 392 |
+
"grad_norm": 0.345845783610871,
|
| 393 |
+
"learning_rate": 2.9818818910417706e-05,
|
| 394 |
+
"loss": 0.6081,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.1011743450767841,
|
| 399 |
+
"grad_norm": 0.29580862920928147,
|
| 400 |
+
"learning_rate": 2.9804644795462437e-05,
|
| 401 |
+
"loss": 0.6121,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.10298102981029811,
|
| 406 |
+
"grad_norm": 0.3175507142787931,
|
| 407 |
+
"learning_rate": 2.9789940556057574e-05,
|
| 408 |
+
"loss": 0.5976,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.10478771454381211,
|
| 413 |
+
"grad_norm": 0.3374272189572956,
|
| 414 |
+
"learning_rate": 2.9774706718732255e-05,
|
| 415 |
+
"loss": 0.6061,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.10659439927732611,
|
| 420 |
+
"grad_norm": 0.27546053233166856,
|
| 421 |
+
"learning_rate": 2.9758943828979444e-05,
|
| 422 |
+
"loss": 0.5922,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.10840108401084012,
|
| 427 |
+
"grad_norm": 0.3657689574287652,
|
| 428 |
+
"learning_rate": 2.9742652451236414e-05,
|
| 429 |
+
"loss": 0.5934,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.1102077687443541,
|
| 434 |
+
"grad_norm": 0.2986956716963071,
|
| 435 |
+
"learning_rate": 2.972583316886451e-05,
|
| 436 |
+
"loss": 0.5971,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.1120144534778681,
|
| 441 |
+
"grad_norm": 0.3448276185716925,
|
| 442 |
+
"learning_rate": 2.9708486584128303e-05,
|
| 443 |
+
"loss": 0.6017,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.11382113821138211,
|
| 448 |
+
"grad_norm": 0.3163562156051723,
|
| 449 |
+
"learning_rate": 2.9690613318173966e-05,
|
| 450 |
+
"loss": 0.6018,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.11562782294489611,
|
| 455 |
+
"grad_norm": 0.2891799826775374,
|
| 456 |
+
"learning_rate": 2.9672214011007087e-05,
|
| 457 |
+
"loss": 0.6001,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.11743450767841011,
|
| 462 |
+
"grad_norm": 0.3052917388689653,
|
| 463 |
+
"learning_rate": 2.9653289321469715e-05,
|
| 464 |
+
"loss": 0.5941,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.11924119241192412,
|
| 469 |
+
"grad_norm": 0.27037779234686826,
|
| 470 |
+
"learning_rate": 2.9633839927216793e-05,
|
| 471 |
+
"loss": 0.5971,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.12104787714543812,
|
| 476 |
+
"grad_norm": 0.2837154841373324,
|
| 477 |
+
"learning_rate": 2.9613866524691867e-05,
|
| 478 |
+
"loss": 0.5873,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.12285456187895212,
|
| 483 |
+
"grad_norm": 0.29318973292150885,
|
| 484 |
+
"learning_rate": 2.9593369829102173e-05,
|
| 485 |
+
"loss": 0.6033,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.12466124661246612,
|
| 490 |
+
"grad_norm": 0.27320922800225206,
|
| 491 |
+
"learning_rate": 2.957235057439301e-05,
|
| 492 |
+
"loss": 0.6043,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.12646793134598014,
|
| 497 |
+
"grad_norm": 0.2888792462126571,
|
| 498 |
+
"learning_rate": 2.955080951322147e-05,
|
| 499 |
+
"loss": 0.609,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.12827461607949414,
|
| 504 |
+
"grad_norm": 0.3010426601423717,
|
| 505 |
+
"learning_rate": 2.9528747416929467e-05,
|
| 506 |
+
"loss": 0.5817,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.13008130081300814,
|
| 511 |
+
"grad_norm": 0.29363653670708806,
|
| 512 |
+
"learning_rate": 2.9506165075516148e-05,
|
| 513 |
+
"loss": 0.599,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.13188798554652212,
|
| 518 |
+
"grad_norm": 0.3695495205161594,
|
| 519 |
+
"learning_rate": 2.9483063297609577e-05,
|
| 520 |
+
"loss": 0.5979,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.13369467028003612,
|
| 525 |
+
"grad_norm": 0.312283280850037,
|
| 526 |
+
"learning_rate": 2.9459442910437798e-05,
|
| 527 |
+
"loss": 0.5894,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.13550135501355012,
|
| 532 |
+
"grad_norm": 0.34410257132188554,
|
| 533 |
+
"learning_rate": 2.94353047597992e-05,
|
| 534 |
+
"loss": 0.5887,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.13730803974706413,
|
| 539 |
+
"grad_norm": 0.2913822090159289,
|
| 540 |
+
"learning_rate": 2.941064971003224e-05,
|
| 541 |
+
"loss": 0.5844,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.13911472448057813,
|
| 546 |
+
"grad_norm": 0.34659905630109983,
|
| 547 |
+
"learning_rate": 2.9385478643984484e-05,
|
| 548 |
+
"loss": 0.5796,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.14092140921409213,
|
| 553 |
+
"grad_norm": 0.3690502006189352,
|
| 554 |
+
"learning_rate": 2.9359792462981007e-05,
|
| 555 |
+
"loss": 0.591,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.14272809394760613,
|
| 560 |
+
"grad_norm": 0.3032664893630925,
|
| 561 |
+
"learning_rate": 2.9333592086792113e-05,
|
| 562 |
+
"loss": 0.5986,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.14453477868112014,
|
| 567 |
+
"grad_norm": 0.34886668595229536,
|
| 568 |
+
"learning_rate": 2.9306878453600382e-05,
|
| 569 |
+
"loss": 0.6077,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.14634146341463414,
|
| 574 |
+
"grad_norm": 0.3308668167904688,
|
| 575 |
+
"learning_rate": 2.9279652519967105e-05,
|
| 576 |
+
"loss": 0.5927,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.14814814814814814,
|
| 581 |
+
"grad_norm": 0.34561229364377843,
|
| 582 |
+
"learning_rate": 2.9251915260798024e-05,
|
| 583 |
+
"loss": 0.585,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.14995483288166214,
|
| 588 |
+
"grad_norm": 0.3315517031152509,
|
| 589 |
+
"learning_rate": 2.9223667669308395e-05,
|
| 590 |
+
"loss": 0.5951,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.15176151761517614,
|
| 595 |
+
"grad_norm": 0.26853290095208654,
|
| 596 |
+
"learning_rate": 2.9194910756987464e-05,
|
| 597 |
+
"loss": 0.5885,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.15356820234869015,
|
| 602 |
+
"grad_norm": 0.29448765107140906,
|
| 603 |
+
"learning_rate": 2.9165645553562215e-05,
|
| 604 |
+
"loss": 0.5914,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.15537488708220415,
|
| 609 |
+
"grad_norm": 0.2806586567612587,
|
| 610 |
+
"learning_rate": 2.9135873106960525e-05,
|
| 611 |
+
"loss": 0.5905,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.15718157181571815,
|
| 616 |
+
"grad_norm": 0.3083804198003563,
|
| 617 |
+
"learning_rate": 2.9105594483273603e-05,
|
| 618 |
+
"loss": 0.5933,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.15898825654923215,
|
| 623 |
+
"grad_norm": 0.29100169406971965,
|
| 624 |
+
"learning_rate": 2.9074810766717865e-05,
|
| 625 |
+
"loss": 0.5971,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.16079494128274616,
|
| 630 |
+
"grad_norm": 0.3123482151135741,
|
| 631 |
+
"learning_rate": 2.904352305959606e-05,
|
| 632 |
+
"loss": 0.594,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.16260162601626016,
|
| 637 |
+
"grad_norm": 0.29086528776110065,
|
| 638 |
+
"learning_rate": 2.9011732482257835e-05,
|
| 639 |
+
"loss": 0.5858,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.16440831074977416,
|
| 644 |
+
"grad_norm": 0.32777518300425235,
|
| 645 |
+
"learning_rate": 2.89794401730596e-05,
|
| 646 |
+
"loss": 0.5838,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.16621499548328816,
|
| 651 |
+
"grad_norm": 0.31282829577117277,
|
| 652 |
+
"learning_rate": 2.894664728832377e-05,
|
| 653 |
+
"loss": 0.5878,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.16802168021680217,
|
| 658 |
+
"grad_norm": 0.30591224241436143,
|
| 659 |
+
"learning_rate": 2.8913355002297367e-05,
|
| 660 |
+
"loss": 0.5943,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.16982836495031617,
|
| 665 |
+
"grad_norm": 0.3454363395865153,
|
| 666 |
+
"learning_rate": 2.887956450710995e-05,
|
| 667 |
+
"loss": 0.5939,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.17163504968383017,
|
| 672 |
+
"grad_norm": 0.3119824836679083,
|
| 673 |
+
"learning_rate": 2.8845277012730963e-05,
|
| 674 |
+
"loss": 0.5859,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.17344173441734417,
|
| 679 |
+
"grad_norm": 0.29451741781860913,
|
| 680 |
+
"learning_rate": 2.8810493746926364e-05,
|
| 681 |
+
"loss": 0.5853,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.17524841915085818,
|
| 686 |
+
"grad_norm": 0.3034863549374876,
|
| 687 |
+
"learning_rate": 2.87752159552147e-05,
|
| 688 |
+
"loss": 0.591,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.17705510388437218,
|
| 693 |
+
"grad_norm": 0.28746917797897076,
|
| 694 |
+
"learning_rate": 2.87394449008225e-05,
|
| 695 |
+
"loss": 0.5841,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.17886178861788618,
|
| 700 |
+
"grad_norm": 0.30996182677103346,
|
| 701 |
+
"learning_rate": 2.8703181864639013e-05,
|
| 702 |
+
"loss": 0.5969,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.18066847335140018,
|
| 707 |
+
"grad_norm": 0.29091619146077263,
|
| 708 |
+
"learning_rate": 2.8666428145170385e-05,
|
| 709 |
+
"loss": 0.5702,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.18247515808491419,
|
| 714 |
+
"grad_norm": 0.2868056287309143,
|
| 715 |
+
"learning_rate": 2.8629185058493116e-05,
|
| 716 |
+
"loss": 0.5862,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.1842818428184282,
|
| 721 |
+
"grad_norm": 0.3505705678502723,
|
| 722 |
+
"learning_rate": 2.8591453938206985e-05,
|
| 723 |
+
"loss": 0.6047,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.1860885275519422,
|
| 728 |
+
"grad_norm": 0.27071275031049963,
|
| 729 |
+
"learning_rate": 2.8553236135387247e-05,
|
| 730 |
+
"loss": 0.5829,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.1878952122854562,
|
| 735 |
+
"grad_norm": 0.33734329421620535,
|
| 736 |
+
"learning_rate": 2.8514533018536286e-05,
|
| 737 |
+
"loss": 0.5811,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.1897018970189702,
|
| 742 |
+
"grad_norm": 0.2770290286284249,
|
| 743 |
+
"learning_rate": 2.8475345973534605e-05,
|
| 744 |
+
"loss": 0.5732,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.1915085817524842,
|
| 749 |
+
"grad_norm": 0.27942020628211717,
|
| 750 |
+
"learning_rate": 2.8435676403591193e-05,
|
| 751 |
+
"loss": 0.576,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.1933152664859982,
|
| 756 |
+
"grad_norm": 0.28553078573573465,
|
| 757 |
+
"learning_rate": 2.8395525729193284e-05,
|
| 758 |
+
"loss": 0.5827,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.1951219512195122,
|
| 763 |
+
"grad_norm": 0.25251226579381214,
|
| 764 |
+
"learning_rate": 2.835489538805548e-05,
|
| 765 |
+
"loss": 0.5802,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.1969286359530262,
|
| 770 |
+
"grad_norm": 0.27568353405316703,
|
| 771 |
+
"learning_rate": 2.8313786835068314e-05,
|
| 772 |
+
"loss": 0.589,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.1987353206865402,
|
| 777 |
+
"grad_norm": 0.27356824941424274,
|
| 778 |
+
"learning_rate": 2.8272201542246077e-05,
|
| 779 |
+
"loss": 0.5708,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.2005420054200542,
|
| 784 |
+
"grad_norm": 0.2930130437286294,
|
| 785 |
+
"learning_rate": 2.8230140998674185e-05,
|
| 786 |
+
"loss": 0.5906,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.2023486901535682,
|
| 791 |
+
"grad_norm": 0.27001628683011253,
|
| 792 |
+
"learning_rate": 2.8187606710455807e-05,
|
| 793 |
+
"loss": 0.584,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2041553748870822,
|
| 798 |
+
"grad_norm": 0.30271557970745333,
|
| 799 |
+
"learning_rate": 2.8144600200657953e-05,
|
| 800 |
+
"loss": 0.5881,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.20596205962059622,
|
| 805 |
+
"grad_norm": 0.3099699158916623,
|
| 806 |
+
"learning_rate": 2.8101123009256946e-05,
|
| 807 |
+
"loss": 0.5711,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.20776874435411022,
|
| 812 |
+
"grad_norm": 0.26752391302167267,
|
| 813 |
+
"learning_rate": 2.8057176693083253e-05,
|
| 814 |
+
"loss": 0.5871,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.20957542908762422,
|
| 819 |
+
"grad_norm": 0.30529403725575444,
|
| 820 |
+
"learning_rate": 2.8012762825765763e-05,
|
| 821 |
+
"loss": 0.5808,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.21138211382113822,
|
| 826 |
+
"grad_norm": 0.30990442497802834,
|
| 827 |
+
"learning_rate": 2.7967882997675424e-05,
|
| 828 |
+
"loss": 0.5921,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.21318879855465223,
|
| 833 |
+
"grad_norm": 0.29406959285002965,
|
| 834 |
+
"learning_rate": 2.7922538815868287e-05,
|
| 835 |
+
"loss": 0.5792,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.21499548328816623,
|
| 840 |
+
"grad_norm": 0.26020193379576106,
|
| 841 |
+
"learning_rate": 2.7876731904027994e-05,
|
| 842 |
+
"loss": 0.5695,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.21680216802168023,
|
| 847 |
+
"grad_norm": 0.3062499009336232,
|
| 848 |
+
"learning_rate": 2.78304639024076e-05,
|
| 849 |
+
"loss": 0.5885,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.2186088527551942,
|
| 854 |
+
"grad_norm": 0.26339824339450146,
|
| 855 |
+
"learning_rate": 2.7783736467770863e-05,
|
| 856 |
+
"loss": 0.5839,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2204155374887082,
|
| 861 |
+
"grad_norm": 0.2997530840298656,
|
| 862 |
+
"learning_rate": 2.7736551273332908e-05,
|
| 863 |
+
"loss": 0.589,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.2222222222222222,
|
| 868 |
+
"grad_norm": 0.30497954819719497,
|
| 869 |
+
"learning_rate": 2.7688910008700305e-05,
|
| 870 |
+
"loss": 0.5787,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.2240289069557362,
|
| 875 |
+
"grad_norm": 0.25400958693406966,
|
| 876 |
+
"learning_rate": 2.764081437981059e-05,
|
| 877 |
+
"loss": 0.5651,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.22583559168925021,
|
| 882 |
+
"grad_norm": 0.27337312352788334,
|
| 883 |
+
"learning_rate": 2.7592266108871158e-05,
|
| 884 |
+
"loss": 0.5721,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.22764227642276422,
|
| 889 |
+
"grad_norm": 0.3015648108540393,
|
| 890 |
+
"learning_rate": 2.754326693429761e-05,
|
| 891 |
+
"loss": 0.5846,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.22944896115627822,
|
| 896 |
+
"grad_norm": 0.3066830899471946,
|
| 897 |
+
"learning_rate": 2.7493818610651493e-05,
|
| 898 |
+
"loss": 0.5773,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.23125564588979222,
|
| 903 |
+
"grad_norm": 0.2557038265672841,
|
| 904 |
+
"learning_rate": 2.744392290857747e-05,
|
| 905 |
+
"loss": 0.5766,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.23306233062330622,
|
| 910 |
+
"grad_norm": 0.28287498283890955,
|
| 911 |
+
"learning_rate": 2.7393581614739924e-05,
|
| 912 |
+
"loss": 0.572,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.23486901535682023,
|
| 917 |
+
"grad_norm": 0.2760546012980017,
|
| 918 |
+
"learning_rate": 2.7342796531758984e-05,
|
| 919 |
+
"loss": 0.5902,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.23667570009033423,
|
| 924 |
+
"grad_norm": 0.29650720341579806,
|
| 925 |
+
"learning_rate": 2.729156947814598e-05,
|
| 926 |
+
"loss": 0.5849,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.23848238482384823,
|
| 931 |
+
"grad_norm": 0.2648334919033985,
|
| 932 |
+
"learning_rate": 2.7239902288238297e-05,
|
| 933 |
+
"loss": 0.5635,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.24028906955736223,
|
| 938 |
+
"grad_norm": 0.2684479411326874,
|
| 939 |
+
"learning_rate": 2.7187796812133733e-05,
|
| 940 |
+
"loss": 0.5789,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.24209575429087624,
|
| 945 |
+
"grad_norm": 0.2903853719359672,
|
| 946 |
+
"learning_rate": 2.7135254915624213e-05,
|
| 947 |
+
"loss": 0.5795,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.24390243902439024,
|
| 952 |
+
"grad_norm": 0.2988296028667376,
|
| 953 |
+
"learning_rate": 2.708227848012901e-05,
|
| 954 |
+
"loss": 0.5771,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.24570912375790424,
|
| 959 |
+
"grad_norm": 0.278887060643492,
|
| 960 |
+
"learning_rate": 2.7028869402627357e-05,
|
| 961 |
+
"loss": 0.5805,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.24751580849141824,
|
| 966 |
+
"grad_norm": 0.3079715134179689,
|
| 967 |
+
"learning_rate": 2.6975029595590523e-05,
|
| 968 |
+
"loss": 0.5643,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.24932249322493225,
|
| 973 |
+
"grad_norm": 0.2797620060845942,
|
| 974 |
+
"learning_rate": 2.6920760986913332e-05,
|
| 975 |
+
"loss": 0.5813,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.25112917795844625,
|
| 980 |
+
"grad_norm": 0.28689667632739463,
|
| 981 |
+
"learning_rate": 2.6866065519845124e-05,
|
| 982 |
+
"loss": 0.5841,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.2529358626919603,
|
| 987 |
+
"grad_norm": 0.2648041926457305,
|
| 988 |
+
"learning_rate": 2.681094515292018e-05,
|
| 989 |
+
"loss": 0.5837,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.25474254742547425,
|
| 994 |
+
"grad_norm": 0.25173007019005905,
|
| 995 |
+
"learning_rate": 2.6755401859887598e-05,
|
| 996 |
+
"loss": 0.5647,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.2565492321589883,
|
| 1001 |
+
"grad_norm": 0.31032191815468113,
|
| 1002 |
+
"learning_rate": 2.6699437629640595e-05,
|
| 1003 |
+
"loss": 0.5843,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.25835591689250226,
|
| 1008 |
+
"grad_norm": 0.2888788250337772,
|
| 1009 |
+
"learning_rate": 2.6643054466145297e-05,
|
| 1010 |
+
"loss": 0.5761,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.2601626016260163,
|
| 1015 |
+
"grad_norm": 0.2760034707559814,
|
| 1016 |
+
"learning_rate": 2.6586254388368995e-05,
|
| 1017 |
+
"loss": 0.5647,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.26196928635953026,
|
| 1022 |
+
"grad_norm": 0.32528080890474936,
|
| 1023 |
+
"learning_rate": 2.652903943020783e-05,
|
| 1024 |
+
"loss": 0.5772,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.26377597109304424,
|
| 1029 |
+
"grad_norm": 0.2637573911390966,
|
| 1030 |
+
"learning_rate": 2.647141164041398e-05,
|
| 1031 |
+
"loss": 0.5821,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.26558265582655827,
|
| 1036 |
+
"grad_norm": 0.2761207440107144,
|
| 1037 |
+
"learning_rate": 2.641337308252228e-05,
|
| 1038 |
+
"loss": 0.5718,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.26738934056007224,
|
| 1043 |
+
"grad_norm": 0.2974380721456416,
|
| 1044 |
+
"learning_rate": 2.6354925834776346e-05,
|
| 1045 |
+
"loss": 0.5733,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.26919602529358627,
|
| 1050 |
+
"grad_norm": 0.2875371174946777,
|
| 1051 |
+
"learning_rate": 2.6296071990054167e-05,
|
| 1052 |
+
"loss": 0.5703,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.27100271002710025,
|
| 1057 |
+
"grad_norm": 0.26400215153050155,
|
| 1058 |
+
"learning_rate": 2.6236813655793123e-05,
|
| 1059 |
+
"loss": 0.5801,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.2728093947606143,
|
| 1064 |
+
"grad_norm": 0.2740289239257524,
|
| 1065 |
+
"learning_rate": 2.617715295391457e-05,
|
| 1066 |
+
"loss": 0.5621,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.27461607949412825,
|
| 1071 |
+
"grad_norm": 0.26263956805016714,
|
| 1072 |
+
"learning_rate": 2.6117092020747824e-05,
|
| 1073 |
+
"loss": 0.5697,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.2764227642276423,
|
| 1078 |
+
"grad_norm": 0.27308995986851226,
|
| 1079 |
+
"learning_rate": 2.6056633006953677e-05,
|
| 1080 |
+
"loss": 0.5697,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.27822944896115626,
|
| 1085 |
+
"grad_norm": 0.2682634840950432,
|
| 1086 |
+
"learning_rate": 2.5995778077447393e-05,
|
| 1087 |
+
"loss": 0.5735,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.2800361336946703,
|
| 1092 |
+
"grad_norm": 0.30213654494482944,
|
| 1093 |
+
"learning_rate": 2.5934529411321174e-05,
|
| 1094 |
+
"loss": 0.5668,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.28184281842818426,
|
| 1099 |
+
"grad_norm": 0.24055343886463815,
|
| 1100 |
+
"learning_rate": 2.587288920176613e-05,
|
| 1101 |
+
"loss": 0.5662,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.2836495031616983,
|
| 1106 |
+
"grad_norm": 0.2913187789114745,
|
| 1107 |
+
"learning_rate": 2.581085965599375e-05,
|
| 1108 |
+
"loss": 0.5795,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.28545618789521227,
|
| 1113 |
+
"grad_norm": 0.2576506841389344,
|
| 1114 |
+
"learning_rate": 2.5748442995156882e-05,
|
| 1115 |
+
"loss": 0.5766,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.2872628726287263,
|
| 1120 |
+
"grad_norm": 0.27596403754545956,
|
| 1121 |
+
"learning_rate": 2.5685641454270172e-05,
|
| 1122 |
+
"loss": 0.5577,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.28906955736224027,
|
| 1127 |
+
"grad_norm": 0.2935051396800575,
|
| 1128 |
+
"learning_rate": 2.5622457282130046e-05,
|
| 1129 |
+
"loss": 0.5668,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.2908762420957543,
|
| 1134 |
+
"grad_norm": 0.261323419986792,
|
| 1135 |
+
"learning_rate": 2.5558892741234173e-05,
|
| 1136 |
+
"loss": 0.5744,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.2926829268292683,
|
| 1141 |
+
"grad_norm": 0.29994364267277224,
|
| 1142 |
+
"learning_rate": 2.5494950107700482e-05,
|
| 1143 |
+
"loss": 0.5606,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.2944896115627823,
|
| 1148 |
+
"grad_norm": 0.25057252176689093,
|
| 1149 |
+
"learning_rate": 2.5430631671185616e-05,
|
| 1150 |
+
"loss": 0.5689,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.2962962962962963,
|
| 1155 |
+
"grad_norm": 0.30439652791987415,
|
| 1156 |
+
"learning_rate": 2.5365939734802973e-05,
|
| 1157 |
+
"loss": 0.5784,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.2981029810298103,
|
| 1162 |
+
"grad_norm": 0.2561891058565834,
|
| 1163 |
+
"learning_rate": 2.5300876615040223e-05,
|
| 1164 |
+
"loss": 0.5693,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.2999096657633243,
|
| 1169 |
+
"grad_norm": 0.30789286843223074,
|
| 1170 |
+
"learning_rate": 2.523544464167637e-05,
|
| 1171 |
+
"loss": 0.5755,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.3017163504968383,
|
| 1176 |
+
"grad_norm": 0.2604413140600789,
|
| 1177 |
+
"learning_rate": 2.5169646157698313e-05,
|
| 1178 |
+
"loss": 0.574,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.3035230352303523,
|
| 1183 |
+
"grad_norm": 0.2772614270807846,
|
| 1184 |
+
"learning_rate": 2.5103483519216964e-05,
|
| 1185 |
+
"loss": 0.5731,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.3053297199638663,
|
| 1190 |
+
"grad_norm": 0.26896696271290815,
|
| 1191 |
+
"learning_rate": 2.5036959095382875e-05,
|
| 1192 |
+
"loss": 0.565,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.3071364046973803,
|
| 1197 |
+
"grad_norm": 0.29065186309501,
|
| 1198 |
+
"learning_rate": 2.4970075268301388e-05,
|
| 1199 |
+
"loss": 0.5783,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.3089430894308943,
|
| 1204 |
+
"grad_norm": 0.2466338266655888,
|
| 1205 |
+
"learning_rate": 2.4902834432947353e-05,
|
| 1206 |
+
"loss": 0.5614,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.3107497741644083,
|
| 1211 |
+
"grad_norm": 0.27214096978444124,
|
| 1212 |
+
"learning_rate": 2.4835238997079382e-05,
|
| 1213 |
+
"loss": 0.5687,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.31255645889792233,
|
| 1218 |
+
"grad_norm": 0.2651928040714497,
|
| 1219 |
+
"learning_rate": 2.4767291381153603e-05,
|
| 1220 |
+
"loss": 0.5719,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.3143631436314363,
|
| 1225 |
+
"grad_norm": 0.23672196782852778,
|
| 1226 |
+
"learning_rate": 2.4698994018236994e-05,
|
| 1227 |
+
"loss": 0.5631,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.31616982836495033,
|
| 1232 |
+
"grad_norm": 0.28356502585206267,
|
| 1233 |
+
"learning_rate": 2.4630349353920284e-05,
|
| 1234 |
+
"loss": 0.5671,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.3179765130984643,
|
| 1239 |
+
"grad_norm": 0.28540875579685554,
|
| 1240 |
+
"learning_rate": 2.4561359846230346e-05,
|
| 1241 |
+
"loss": 0.5818,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.31978319783197834,
|
| 1246 |
+
"grad_norm": 0.24190126114290808,
|
| 1247 |
+
"learning_rate": 2.4492027965542217e-05,
|
| 1248 |
+
"loss": 0.5569,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.3215898825654923,
|
| 1253 |
+
"grad_norm": 0.27287155700655424,
|
| 1254 |
+
"learning_rate": 2.44223561944906e-05,
|
| 1255 |
+
"loss": 0.5643,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.32339656729900634,
|
| 1260 |
+
"grad_norm": 0.24924695151585574,
|
| 1261 |
+
"learning_rate": 2.4352347027881003e-05,
|
| 1262 |
+
"loss": 0.5738,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.3252032520325203,
|
| 1267 |
+
"grad_norm": 0.2759090650898249,
|
| 1268 |
+
"learning_rate": 2.4282002972600382e-05,
|
| 1269 |
+
"loss": 0.5817,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.32700993676603435,
|
| 1274 |
+
"grad_norm": 0.22785083526499783,
|
| 1275 |
+
"learning_rate": 2.4211326547527377e-05,
|
| 1276 |
+
"loss": 0.5601,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.3288166214995483,
|
| 1281 |
+
"grad_norm": 0.2691907674221595,
|
| 1282 |
+
"learning_rate": 2.4140320283442125e-05,
|
| 1283 |
+
"loss": 0.5699,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.33062330623306235,
|
| 1288 |
+
"grad_norm": 0.2708392714868768,
|
| 1289 |
+
"learning_rate": 2.4068986722935625e-05,
|
| 1290 |
+
"loss": 0.5806,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.3324299909665763,
|
| 1295 |
+
"grad_norm": 0.27339466736189244,
|
| 1296 |
+
"learning_rate": 2.3997328420318705e-05,
|
| 1297 |
+
"loss": 0.5769,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.33423667570009036,
|
| 1302 |
+
"grad_norm": 0.26435674776037377,
|
| 1303 |
+
"learning_rate": 2.3925347941530556e-05,
|
| 1304 |
+
"loss": 0.5733,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.33604336043360433,
|
| 1309 |
+
"grad_norm": 0.26341316111660884,
|
| 1310 |
+
"learning_rate": 2.3853047864046843e-05,
|
| 1311 |
+
"loss": 0.5684,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.33785004516711836,
|
| 1316 |
+
"grad_norm": 0.27858160542364235,
|
| 1317 |
+
"learning_rate": 2.3780430776787413e-05,
|
| 1318 |
+
"loss": 0.5658,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.33965672990063234,
|
| 1323 |
+
"grad_norm": 0.23833042598843737,
|
| 1324 |
+
"learning_rate": 2.3707499280023604e-05,
|
| 1325 |
+
"loss": 0.5655,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.34146341463414637,
|
| 1330 |
+
"grad_norm": 0.2808631689375272,
|
| 1331 |
+
"learning_rate": 2.3634255985285104e-05,
|
| 1332 |
+
"loss": 0.5729,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.34327009936766034,
|
| 1337 |
+
"grad_norm": 0.25111983735673515,
|
| 1338 |
+
"learning_rate": 2.356070351526648e-05,
|
| 1339 |
+
"loss": 0.562,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.34507678410117437,
|
| 1344 |
+
"grad_norm": 0.2571681206798971,
|
| 1345 |
+
"learning_rate": 2.348684450373322e-05,
|
| 1346 |
+
"loss": 0.5599,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.34688346883468835,
|
| 1351 |
+
"grad_norm": 0.2409025648925046,
|
| 1352 |
+
"learning_rate": 2.3412681595427467e-05,
|
| 1353 |
+
"loss": 0.5674,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.3486901535682023,
|
| 1358 |
+
"grad_norm": 0.29444654953284566,
|
| 1359 |
+
"learning_rate": 2.3338217445973268e-05,
|
| 1360 |
+
"loss": 0.5687,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.35049683830171635,
|
| 1365 |
+
"grad_norm": 0.2496920890877963,
|
| 1366 |
+
"learning_rate": 2.3263454721781537e-05,
|
| 1367 |
+
"loss": 0.5705,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.3523035230352303,
|
| 1372 |
+
"grad_norm": 0.27467425910302257,
|
| 1373 |
+
"learning_rate": 2.318839609995453e-05,
|
| 1374 |
+
"loss": 0.5536,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.35411020776874436,
|
| 1379 |
+
"grad_norm": 0.25067206006192067,
|
| 1380 |
+
"learning_rate": 2.3113044268189995e-05,
|
| 1381 |
+
"loss": 0.5668,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.35591689250225833,
|
| 1386 |
+
"grad_norm": 0.25127765224467463,
|
| 1387 |
+
"learning_rate": 2.303740192468495e-05,
|
| 1388 |
+
"loss": 0.5671,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.35772357723577236,
|
| 1393 |
+
"grad_norm": 0.2742190997822365,
|
| 1394 |
+
"learning_rate": 2.2961471778039045e-05,
|
| 1395 |
+
"loss": 0.5436,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.35953026196928634,
|
| 1400 |
+
"grad_norm": 0.2617420424365515,
|
| 1401 |
+
"learning_rate": 2.288525654715757e-05,
|
| 1402 |
+
"loss": 0.567,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.36133694670280037,
|
| 1407 |
+
"grad_norm": 0.2601868662327404,
|
| 1408 |
+
"learning_rate": 2.280875896115413e-05,
|
| 1409 |
+
"loss": 0.556,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.36314363143631434,
|
| 1414 |
+
"grad_norm": 0.2488467816010916,
|
| 1415 |
+
"learning_rate": 2.2731981759252876e-05,
|
| 1416 |
+
"loss": 0.5506,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.36495031616982837,
|
| 1421 |
+
"grad_norm": 0.24184725633849133,
|
| 1422 |
+
"learning_rate": 2.2654927690690445e-05,
|
| 1423 |
+
"loss": 0.5773,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.36675700090334235,
|
| 1428 |
+
"grad_norm": 0.25373414117124127,
|
| 1429 |
+
"learning_rate": 2.257759951461752e-05,
|
| 1430 |
+
"loss": 0.5641,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.3685636856368564,
|
| 1435 |
+
"grad_norm": 0.26564822413876754,
|
| 1436 |
+
"learning_rate": 2.25e-05,
|
| 1437 |
+
"loss": 0.5773,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.37037037037037035,
|
| 1442 |
+
"grad_norm": 0.22934416047361944,
|
| 1443 |
+
"learning_rate": 2.24221319255199e-05,
|
| 1444 |
+
"loss": 0.5677,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.3721770551038844,
|
| 1449 |
+
"grad_norm": 0.27064508142785815,
|
| 1450 |
+
"learning_rate": 2.234399807947579e-05,
|
| 1451 |
+
"loss": 0.5548,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.37398373983739835,
|
| 1456 |
+
"grad_norm": 0.2371896313671772,
|
| 1457 |
+
"learning_rate": 2.2265601259683e-05,
|
| 1458 |
+
"loss": 0.5627,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.3757904245709124,
|
| 1463 |
+
"grad_norm": 0.24008373009834236,
|
| 1464 |
+
"learning_rate": 2.2186944273373426e-05,
|
| 1465 |
+
"loss": 0.5499,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.37759710930442636,
|
| 1470 |
+
"grad_norm": 0.25685866079731606,
|
| 1471 |
+
"learning_rate": 2.210802993709498e-05,
|
| 1472 |
+
"loss": 0.5717,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.3794037940379404,
|
| 1477 |
+
"grad_norm": 0.2629866117258039,
|
| 1478 |
+
"learning_rate": 2.202886107661078e-05,
|
| 1479 |
+
"loss": 0.5676,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.38121047877145436,
|
| 1484 |
+
"grad_norm": 0.2522800121206238,
|
| 1485 |
+
"learning_rate": 2.1949440526797928e-05,
|
| 1486 |
+
"loss": 0.5669,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.3830171635049684,
|
| 1491 |
+
"grad_norm": 0.2540123635971477,
|
| 1492 |
+
"learning_rate": 2.1869771131546015e-05,
|
| 1493 |
+
"loss": 0.5746,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.38482384823848237,
|
| 1498 |
+
"grad_norm": 0.2673805985713425,
|
| 1499 |
+
"learning_rate": 2.178985574365529e-05,
|
| 1500 |
+
"loss": 0.5751,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.3866305329719964,
|
| 1505 |
+
"grad_norm": 0.26844790033448696,
|
| 1506 |
+
"learning_rate": 2.170969722473449e-05,
|
| 1507 |
+
"loss": 0.5608,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.3884372177055104,
|
| 1512 |
+
"grad_norm": 0.3287228900436167,
|
| 1513 |
+
"learning_rate": 2.1629298445098403e-05,
|
| 1514 |
+
"loss": 0.5881,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.3902439024390244,
|
| 1519 |
+
"grad_norm": 0.24641908304543073,
|
| 1520 |
+
"learning_rate": 2.154866228366505e-05,
|
| 1521 |
+
"loss": 0.5767,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.3920505871725384,
|
| 1526 |
+
"grad_norm": 0.2356470126020688,
|
| 1527 |
+
"learning_rate": 2.146779162785263e-05,
|
| 1528 |
+
"loss": 0.5768,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.3938572719060524,
|
| 1533 |
+
"grad_norm": 0.26263666882985864,
|
| 1534 |
+
"learning_rate": 2.138668937347609e-05,
|
| 1535 |
+
"loss": 0.5683,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.3956639566395664,
|
| 1540 |
+
"grad_norm": 0.23701425043610796,
|
| 1541 |
+
"learning_rate": 2.1305358424643484e-05,
|
| 1542 |
+
"loss": 0.5634,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.3974706413730804,
|
| 1547 |
+
"grad_norm": 0.24138606059569664,
|
| 1548 |
+
"learning_rate": 2.1223801693651927e-05,
|
| 1549 |
+
"loss": 0.5656,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.3992773261065944,
|
| 1554 |
+
"grad_norm": 0.2595567201221021,
|
| 1555 |
+
"learning_rate": 2.114202210088336e-05,
|
| 1556 |
+
"loss": 0.5546,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.4010840108401084,
|
| 1561 |
+
"grad_norm": 0.2491513558591219,
|
| 1562 |
+
"learning_rate": 2.106002257469993e-05,
|
| 1563 |
+
"loss": 0.5718,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.4028906955736224,
|
| 1568 |
+
"grad_norm": 0.2486982800205461,
|
| 1569 |
+
"learning_rate": 2.0977806051339172e-05,
|
| 1570 |
+
"loss": 0.5551,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.4046973803071364,
|
| 1575 |
+
"grad_norm": 0.23727864667012805,
|
| 1576 |
+
"learning_rate": 2.0895375474808857e-05,
|
| 1577 |
+
"loss": 0.559,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.4065040650406504,
|
| 1582 |
+
"grad_norm": 0.287906688283815,
|
| 1583 |
+
"learning_rate": 2.0812733796781544e-05,
|
| 1584 |
+
"loss": 0.5648,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.4083107497741644,
|
| 1589 |
+
"grad_norm": 0.23398485566681798,
|
| 1590 |
+
"learning_rate": 2.0729883976488936e-05,
|
| 1591 |
+
"loss": 0.5699,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.4101174345076784,
|
| 1596 |
+
"grad_norm": 0.2672121559206604,
|
| 1597 |
+
"learning_rate": 2.064682898061588e-05,
|
| 1598 |
+
"loss": 0.5745,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.41192411924119243,
|
| 1603 |
+
"grad_norm": 0.25274044632247594,
|
| 1604 |
+
"learning_rate": 2.0563571783194146e-05,
|
| 1605 |
+
"loss": 0.5607,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.4137308039747064,
|
| 1610 |
+
"grad_norm": 0.23024580592682378,
|
| 1611 |
+
"learning_rate": 2.0480115365495928e-05,
|
| 1612 |
+
"loss": 0.5633,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.41553748870822044,
|
| 1617 |
+
"grad_norm": 0.2643430047659416,
|
| 1618 |
+
"learning_rate": 2.0396462715927107e-05,
|
| 1619 |
+
"loss": 0.5657,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.4173441734417344,
|
| 1624 |
+
"grad_norm": 0.24590645504611103,
|
| 1625 |
+
"learning_rate": 2.0312616829920222e-05,
|
| 1626 |
+
"loss": 0.5651,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.41915085817524844,
|
| 1631 |
+
"grad_norm": 0.232079984180177,
|
| 1632 |
+
"learning_rate": 2.022858070982723e-05,
|
| 1633 |
+
"loss": 0.5676,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.4209575429087624,
|
| 1638 |
+
"grad_norm": 0.23416214443037042,
|
| 1639 |
+
"learning_rate": 2.0144357364811973e-05,
|
| 1640 |
+
"loss": 0.5501,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.42276422764227645,
|
| 1645 |
+
"grad_norm": 0.24394361384059154,
|
| 1646 |
+
"learning_rate": 2.0059949810742452e-05,
|
| 1647 |
+
"loss": 0.565,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.4245709123757904,
|
| 1652 |
+
"grad_norm": 0.22171860398747742,
|
| 1653 |
+
"learning_rate": 1.997536107008281e-05,
|
| 1654 |
+
"loss": 0.5603,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.42637759710930445,
|
| 1659 |
+
"grad_norm": 0.2573737818729415,
|
| 1660 |
+
"learning_rate": 1.9890594171785128e-05,
|
| 1661 |
+
"loss": 0.5718,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.4281842818428184,
|
| 1666 |
+
"grad_norm": 0.24929065928195437,
|
| 1667 |
+
"learning_rate": 1.9805652151180945e-05,
|
| 1668 |
+
"loss": 0.5716,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.42999096657633246,
|
| 1673 |
+
"grad_norm": 0.22521672092224404,
|
| 1674 |
+
"learning_rate": 1.972053804987258e-05,
|
| 1675 |
+
"loss": 0.5799,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.43179765130984643,
|
| 1680 |
+
"grad_norm": 0.2400133312081751,
|
| 1681 |
+
"learning_rate": 1.963525491562421e-05,
|
| 1682 |
+
"loss": 0.5607,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.43360433604336046,
|
| 1687 |
+
"grad_norm": 0.2220251642670775,
|
| 1688 |
+
"learning_rate": 1.954980580225275e-05,
|
| 1689 |
+
"loss": 0.5613,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.43541102077687444,
|
| 1694 |
+
"grad_norm": 0.24242836746273963,
|
| 1695 |
+
"learning_rate": 1.946419376951848e-05,
|
| 1696 |
+
"loss": 0.5601,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.4372177055103884,
|
| 1701 |
+
"grad_norm": 0.23280796509155544,
|
| 1702 |
+
"learning_rate": 1.9378421883015505e-05,
|
| 1703 |
+
"loss": 0.5608,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.43902439024390244,
|
| 1708 |
+
"grad_norm": 0.2424520004437008,
|
| 1709 |
+
"learning_rate": 1.9292493214061953e-05,
|
| 1710 |
+
"loss": 0.5653,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.4408310749774164,
|
| 1715 |
+
"grad_norm": 0.21938548719470424,
|
| 1716 |
+
"learning_rate": 1.9206410839590042e-05,
|
| 1717 |
+
"loss": 0.5713,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.44263775971093045,
|
| 1722 |
+
"grad_norm": 0.2873818775831322,
|
| 1723 |
+
"learning_rate": 1.9120177842035853e-05,
|
| 1724 |
+
"loss": 0.5635,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.4444444444444444,
|
| 1729 |
+
"grad_norm": 0.24359879240501903,
|
| 1730 |
+
"learning_rate": 1.9033797309228984e-05,
|
| 1731 |
+
"loss": 0.5703,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.44625112917795845,
|
| 1736 |
+
"grad_norm": 0.2357242641893439,
|
| 1737 |
+
"learning_rate": 1.8947272334281977e-05,
|
| 1738 |
+
"loss": 0.5521,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.4480578139114724,
|
| 1743 |
+
"grad_norm": 0.2462690537681842,
|
| 1744 |
+
"learning_rate": 1.8860606015479537e-05,
|
| 1745 |
+
"loss": 0.5706,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.44986449864498645,
|
| 1750 |
+
"grad_norm": 0.23970905475638837,
|
| 1751 |
+
"learning_rate": 1.877380145616763e-05,
|
| 1752 |
+
"loss": 0.5543,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.45167118337850043,
|
| 1757 |
+
"grad_norm": 0.25559374336438795,
|
| 1758 |
+
"learning_rate": 1.868686176464232e-05,
|
| 1759 |
+
"loss": 0.5694,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.45347786811201446,
|
| 1764 |
+
"grad_norm": 0.22667022533452194,
|
| 1765 |
+
"learning_rate": 1.8599790054038487e-05,
|
| 1766 |
+
"loss": 0.5563,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.45528455284552843,
|
| 1771 |
+
"grad_norm": 0.2328027982974321,
|
| 1772 |
+
"learning_rate": 1.8512589442218358e-05,
|
| 1773 |
+
"loss": 0.5384,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.45709123757904246,
|
| 1778 |
+
"grad_norm": 0.2490658489853876,
|
| 1779 |
+
"learning_rate": 1.8425263051659838e-05,
|
| 1780 |
+
"loss": 0.5613,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.45889792231255644,
|
| 1785 |
+
"grad_norm": 0.25086634603487334,
|
| 1786 |
+
"learning_rate": 1.8337814009344716e-05,
|
| 1787 |
+
"loss": 0.5602,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.46070460704607047,
|
| 1792 |
+
"grad_norm": 0.25605732223142635,
|
| 1793 |
+
"learning_rate": 1.8250245446646707e-05,
|
| 1794 |
+
"loss": 0.5535,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.46251129177958444,
|
| 1799 |
+
"grad_norm": 0.26469759888755845,
|
| 1800 |
+
"learning_rate": 1.8162560499219286e-05,
|
| 1801 |
+
"loss": 0.5537,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.4643179765130985,
|
| 1806 |
+
"grad_norm": 0.2476106293930312,
|
| 1807 |
+
"learning_rate": 1.807476230688346e-05,
|
| 1808 |
+
"loss": 0.5644,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.46612466124661245,
|
| 1813 |
+
"grad_norm": 0.2611791488235218,
|
| 1814 |
+
"learning_rate": 1.7986854013515274e-05,
|
| 1815 |
+
"loss": 0.5589,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.4679313459801265,
|
| 1820 |
+
"grad_norm": 0.25614740455319657,
|
| 1821 |
+
"learning_rate": 1.78988387669333e-05,
|
| 1822 |
+
"loss": 0.5626,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.46973803071364045,
|
| 1827 |
+
"grad_norm": 0.26413847448296346,
|
| 1828 |
+
"learning_rate": 1.781071971878587e-05,
|
| 1829 |
+
"loss": 0.5763,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.4715447154471545,
|
| 1834 |
+
"grad_norm": 0.2670037728752572,
|
| 1835 |
+
"learning_rate": 1.7722500024438244e-05,
|
| 1836 |
+
"loss": 0.5671,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.47335140018066846,
|
| 1841 |
+
"grad_norm": 0.2655083894599294,
|
| 1842 |
+
"learning_rate": 1.7634182842859628e-05,
|
| 1843 |
+
"loss": 0.5556,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.4751580849141825,
|
| 1848 |
+
"grad_norm": 0.2602266219558274,
|
| 1849 |
+
"learning_rate": 1.7545771336510033e-05,
|
| 1850 |
+
"loss": 0.5603,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.47696476964769646,
|
| 1855 |
+
"grad_norm": 0.23837446328300185,
|
| 1856 |
+
"learning_rate": 1.7457268671227067e-05,
|
| 1857 |
+
"loss": 0.5661,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.4787714543812105,
|
| 1862 |
+
"grad_norm": 0.2855243343978605,
|
| 1863 |
+
"learning_rate": 1.736867801611254e-05,
|
| 1864 |
+
"loss": 0.5479,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.48057813911472447,
|
| 1869 |
+
"grad_norm": 0.23335711495710984,
|
| 1870 |
+
"learning_rate": 1.728000254341901e-05,
|
| 1871 |
+
"loss": 0.5717,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.4823848238482385,
|
| 1876 |
+
"grad_norm": 0.2257992261469873,
|
| 1877 |
+
"learning_rate": 1.7191245428436175e-05,
|
| 1878 |
+
"loss": 0.5566,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.48419150858175247,
|
| 1883 |
+
"grad_norm": 0.23986035421561297,
|
| 1884 |
+
"learning_rate": 1.7102409849377188e-05,
|
| 1885 |
+
"loss": 0.5563,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.4859981933152665,
|
| 1890 |
+
"grad_norm": 0.22957382135670054,
|
| 1891 |
+
"learning_rate": 1.7013498987264832e-05,
|
| 1892 |
+
"loss": 0.5634,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.4878048780487805,
|
| 1897 |
+
"grad_norm": 0.2332081125649847,
|
| 1898 |
+
"learning_rate": 1.6924516025817636e-05,
|
| 1899 |
+
"loss": 0.5448,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.4896115627822945,
|
| 1904 |
+
"grad_norm": 0.2358236013629391,
|
| 1905 |
+
"learning_rate": 1.683546415133584e-05,
|
| 1906 |
+
"loss": 0.5663,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.4914182475158085,
|
| 1911 |
+
"grad_norm": 0.2651609439225248,
|
| 1912 |
+
"learning_rate": 1.6746346552587342e-05,
|
| 1913 |
+
"loss": 0.561,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.4932249322493225,
|
| 1918 |
+
"grad_norm": 0.25056099802020176,
|
| 1919 |
+
"learning_rate": 1.665716642069349e-05,
|
| 1920 |
+
"loss": 0.5689,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.4950316169828365,
|
| 1925 |
+
"grad_norm": 0.2699052892919483,
|
| 1926 |
+
"learning_rate": 1.6567926949014805e-05,
|
| 1927 |
+
"loss": 0.5567,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.4968383017163505,
|
| 1932 |
+
"grad_norm": 0.23647220641096864,
|
| 1933 |
+
"learning_rate": 1.6478631333036655e-05,
|
| 1934 |
+
"loss": 0.5507,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.4986449864498645,
|
| 1939 |
+
"grad_norm": 0.21602219843408765,
|
| 1940 |
+
"learning_rate": 1.638928277025482e-05,
|
| 1941 |
+
"loss": 0.5432,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.5004516711833785,
|
| 1946 |
+
"grad_norm": 0.2354573231695346,
|
| 1947 |
+
"learning_rate": 1.6299884460061005e-05,
|
| 1948 |
+
"loss": 0.5547,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.5022583559168925,
|
| 1953 |
+
"grad_norm": 0.2197114014140093,
|
| 1954 |
+
"learning_rate": 1.621043960362826e-05,
|
| 1955 |
+
"loss": 0.5418,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.5040650406504065,
|
| 1960 |
+
"grad_norm": 0.23257701295408562,
|
| 1961 |
+
"learning_rate": 1.6120951403796367e-05,
|
| 1962 |
+
"loss": 0.5568,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.5058717253839206,
|
| 1967 |
+
"grad_norm": 0.24433486985285227,
|
| 1968 |
+
"learning_rate": 1.603142306495714e-05,
|
| 1969 |
+
"loss": 0.553,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.5076784101174345,
|
| 1974 |
+
"grad_norm": 0.20527397519546922,
|
| 1975 |
+
"learning_rate": 1.5941857792939702e-05,
|
| 1976 |
+
"loss": 0.554,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.5094850948509485,
|
| 1981 |
+
"grad_norm": 0.22929324716898536,
|
| 1982 |
+
"learning_rate": 1.585225879489567e-05,
|
| 1983 |
+
"loss": 0.5487,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.5112917795844625,
|
| 1988 |
+
"grad_norm": 0.2238089603853136,
|
| 1989 |
+
"learning_rate": 1.5762629279184326e-05,
|
| 1990 |
+
"loss": 0.5634,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.5130984643179766,
|
| 1995 |
+
"grad_norm": 0.22412925067398695,
|
| 1996 |
+
"learning_rate": 1.5672972455257726e-05,
|
| 1997 |
+
"loss": 0.5518,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.5149051490514905,
|
| 2002 |
+
"grad_norm": 0.23076070566516943,
|
| 2003 |
+
"learning_rate": 1.5583291533545775e-05,
|
| 2004 |
+
"loss": 0.5463,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.5167118337850045,
|
| 2009 |
+
"grad_norm": 0.23140896156408275,
|
| 2010 |
+
"learning_rate": 1.549358972534128e-05,
|
| 2011 |
+
"loss": 0.5437,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.5185185185185185,
|
| 2016 |
+
"grad_norm": 0.22643479753851717,
|
| 2017 |
+
"learning_rate": 1.5403870242684942e-05,
|
| 2018 |
+
"loss": 0.5651,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.5203252032520326,
|
| 2023 |
+
"grad_norm": 0.24172544315368483,
|
| 2024 |
+
"learning_rate": 1.5314136298250355e-05,
|
| 2025 |
+
"loss": 0.5625,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.5221318879855466,
|
| 2030 |
+
"grad_norm": 0.21456673351384214,
|
| 2031 |
+
"learning_rate": 1.5224391105228956e-05,
|
| 2032 |
+
"loss": 0.547,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.5239385727190605,
|
| 2037 |
+
"grad_norm": 0.20236395606188895,
|
| 2038 |
+
"learning_rate": 1.5134637877214968e-05,
|
| 2039 |
+
"loss": 0.5588,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.5257452574525745,
|
| 2044 |
+
"grad_norm": 0.23554049753605505,
|
| 2045 |
+
"learning_rate": 1.5044879828090346e-05,
|
| 2046 |
+
"loss": 0.5631,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.5275519421860885,
|
| 2051 |
+
"grad_norm": 0.22947805697224488,
|
| 2052 |
+
"learning_rate": 1.4955120171909658e-05,
|
| 2053 |
+
"loss": 0.5669,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.5293586269196026,
|
| 2058 |
+
"grad_norm": 0.1986163494264529,
|
| 2059 |
+
"learning_rate": 1.4865362122785031e-05,
|
| 2060 |
+
"loss": 0.5595,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.5311653116531165,
|
| 2065 |
+
"grad_norm": 0.22657031125938396,
|
| 2066 |
+
"learning_rate": 1.4775608894771048e-05,
|
| 2067 |
+
"loss": 0.5519,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.5329719963866305,
|
| 2072 |
+
"grad_norm": 0.26178909293346697,
|
| 2073 |
+
"learning_rate": 1.4685863701749648e-05,
|
| 2074 |
+
"loss": 0.5497,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.5347786811201445,
|
| 2079 |
+
"grad_norm": 0.24491042948023758,
|
| 2080 |
+
"learning_rate": 1.4596129757315062e-05,
|
| 2081 |
+
"loss": 0.5537,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.5365853658536586,
|
| 2086 |
+
"grad_norm": 0.234622033552508,
|
| 2087 |
+
"learning_rate": 1.4506410274658718e-05,
|
| 2088 |
+
"loss": 0.5586,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.5383920505871725,
|
| 2093 |
+
"grad_norm": 0.23622066572903277,
|
| 2094 |
+
"learning_rate": 1.441670846645423e-05,
|
| 2095 |
+
"loss": 0.5533,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.5401987353206865,
|
| 2100 |
+
"grad_norm": 0.24071443512391985,
|
| 2101 |
+
"learning_rate": 1.4327027544742281e-05,
|
| 2102 |
+
"loss": 0.5685,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.5420054200542005,
|
| 2107 |
+
"grad_norm": 0.22544308961774373,
|
| 2108 |
+
"learning_rate": 1.4237370720815675e-05,
|
| 2109 |
+
"loss": 0.5566,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
}
|
| 2112 |
+
],
|
| 2113 |
+
"logging_steps": 1,
|
| 2114 |
+
"max_steps": 553,
|
| 2115 |
+
"num_input_tokens_seen": 0,
|
| 2116 |
+
"num_train_epochs": 1,
|
| 2117 |
+
"save_steps": 100,
|
| 2118 |
+
"stateful_callbacks": {
|
| 2119 |
+
"TrainerControl": {
|
| 2120 |
+
"args": {
|
| 2121 |
+
"should_epoch_stop": false,
|
| 2122 |
+
"should_evaluate": false,
|
| 2123 |
+
"should_log": false,
|
| 2124 |
+
"should_save": true,
|
| 2125 |
+
"should_training_stop": false
|
| 2126 |
+
},
|
| 2127 |
+
"attributes": {}
|
| 2128 |
+
}
|
| 2129 |
+
},
|
| 2130 |
+
"total_flos": 347755278106624.0,
|
| 2131 |
+
"train_batch_size": 2,
|
| 2132 |
+
"trial_name": null,
|
| 2133 |
+
"trial_params": null
|
| 2134 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e17e9ef49452dfbb88bdb398539e0416fca0be014460bc3a0231be831d4c7664
|
| 3 |
+
size 8017
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|